Instructions to use mrcuddle/Test-URPM-SD2.1Unclip with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use mrcuddle/Test-URPM-SD2.1Unclip with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("mrcuddle/Test-URPM-SD2.1Unclip", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Uber Realistic Porn Merge SD2.1Unclip
For scientific research purposes
Model Description
I basically did an add-difference interpolation merge:
Merge = Unclip + (URPM − Base)*1
The model will generate random images if provided with an empty prompt or random latent.
These result images are surprisingly coherent (view notebook).
It's assumed to otherwise function identically to the base finetune.
Notebook
I've uploaded the Jupyter Notebook used to create the model.
Further Development
I'd suggest adding LoRAs to help "guiding" the result.
- Downloads last month
- 6